This is an automated email from the ASF dual-hosted git repository. areusch pushed a commit to branch ci-docker-staging in repository https://gitbox.apache.org/repos/asf/tvm.git
commit 0bda958dab567314ebfa13b3e0c22c1d88de27a1 Merge: f0796a6 431a7d6 Author: Andrew Reusch <[email protected]> AuthorDate: Fri Mar 19 14:23:03 2021 -0700 Merge remote-tracking branch 'origin/main' into test_mdw_qemu_changes .gitmodules | 3 + 3rdparty/libbacktrace | 1 + CMakeLists.txt | 63 ++- CONTRIBUTORS.md | 1 + .../android_camera/app/src/main/jni/Application.mk | 4 +- apps/android_camera/app/src/main/jni/tvm_runtime.h | 38 +- .../android_deploy/app/src/main/jni/Application.mk | 2 +- apps/android_deploy/app/src/main/jni/tvm_runtime.h | 3 + apps/android_rpc/app/src/main/jni/Application.mk | 2 +- apps/android_rpc/app/src/main/jni/tvm_runtime.h | 36 +- apps/bundle_deploy/Makefile | 6 +- apps/dso_plugin_module/Makefile | 3 +- apps/extension/Makefile | 3 +- apps/ios_rpc/tvmrpc.xcodeproj/project.pbxproj | 6 + apps/ios_rpc/tvmrpc/TVMRuntime.h | 2 +- apps/ios_rpc/tvmrpc/TVMRuntime.mm | 16 +- apps/ios_rpc/tvmrpc/ViewController.mm | 4 +- cmake/config.cmake | 8 + cmake/modules/CUDA.cmake | 11 + cmake/modules/Libbacktrace.cmake | 45 +++ cmake/modules/VTA.cmake | 3 + golang/Makefile | 2 +- include/tvm/ir/attrs.h | 4 +- include/tvm/ir/diagnostic.h | 9 + include/tvm/ir/error.h | 26 +- include/tvm/ir/type_relation.h | 2 +- include/tvm/relay/analysis.h | 2 +- include/tvm/runtime/container.h | 1 + include/tvm/runtime/data_type.h | 2 +- include/tvm/runtime/logging.h | 438 +++++++++++++++++++++ include/tvm/runtime/object.h | 2 +- include/tvm/runtime/packed_func.h | 6 +- include/tvm/runtime/vm/bytecode.h | 2 +- include/tvm/support/logging.h | 158 -------- include/tvm/support/with.h | 2 +- licenses/LICENSE.libbacktrace.txt | 29 ++ python/setup.py | 2 +- python/tvm/_ffi/base.py | 4 +- python/tvm/contrib/cc.py | 16 +- .../tvm/contrib/cuda_graph/__init__.py | 3 - .../tvm/contrib/cuda_graph/cuda_graph_runtime.py | 134 +++++++ python/tvm/contrib/nvcc.py | 12 + python/tvm/driver/tvmc/frontends.py | 27 +- python/tvm/micro/build.py | 2 +- python/tvm/relay/frontend/pytorch.py | 29 +- python/tvm/relay/frontend/tensorflow.py | 54 ++- python/tvm/relay/testing/darknet.py | 2 +- python/tvm/relay/transform/transform.py | 26 +- python/tvm/runtime/module.py | 3 + python/tvm/testing.py | 19 + python/tvm/topi/cuda/batch_matmul.py | 7 +- python/tvm/topi/cuda/dense.py | 11 +- src/auto_scheduler/compute_dag.cc | 2 +- src/auto_scheduler/feature.cc | 2 +- .../search_policy/sketch_policy_rules.cc | 4 +- src/auto_scheduler/transform_step.cc | 2 +- src/ir/error.cc | 3 +- src/parser/parser.cc | 8 +- src/parser/span_check.h | 2 +- src/relay/analysis/annotated_region_set.cc | 5 +- src/relay/analysis/kind_check.cc | 2 +- src/relay/analysis/type_solver.cc | 4 +- src/relay/analysis/well_formed.cc | 2 +- src/relay/backend/contrib/codegen_c/codegen_c.h | 2 + src/relay/backend/vm/compiler.cc | 2 +- src/relay/backend/vm/compiler.h | 2 +- src/relay/backend/vm/inline_primitives.cc | 2 +- src/relay/backend/vm/lambda_lift.cc | 2 +- src/relay/backend/vm/removed_unused_funcs.cc | 2 +- src/relay/op/nn/convolution.h | 2 +- src/relay/op/nn/nn.cc | 1 + src/relay/op/tensor/transform.cc | 12 +- src/relay/op/tensor/transform.h | 4 +- src/relay/op/type_relations.cc | 2 +- src/relay/qnn/op/concatenate.cc | 14 +- src/relay/transforms/first_order_gradient.cc | 309 +++++++++++++++ src/relay/transforms/fold_explicit_padding.cc | 2 +- .../nnpack_utils.h => relay/transforms/gradient.h} | 45 ++- .../{gradient.cc => higher_order_gradient.cc} | 274 +------------ src/relay/transforms/inline.cc | 2 +- src/relay/transforms/memory_alloc.cc | 2 +- src/relay/transforms/partial_eval.cc | 4 +- src/relay/transforms/simplify_expr.cc | 2 +- src/relay/transforms/to_a_normal_form.cc | 2 +- src/relay/transforms/to_basic_block_normal_form.cc | 2 +- src/relay/transforms/type_infer.cc | 2 +- src/runtime/c_runtime_api.cc | 6 +- src/runtime/contrib/cblas/cblas.cc | 2 +- src/runtime/contrib/cblas/mkl.cc | 2 +- src/runtime/contrib/cblas/mkldnn.cc | 2 +- src/runtime/contrib/cublas/cublas.cc | 2 +- src/runtime/contrib/cublas/cublas_utils.h | 2 +- src/runtime/contrib/cudnn/cudnn_utils.h | 2 +- src/runtime/contrib/miopen/miopen_utils.h | 2 +- src/runtime/contrib/mps/mps_utils.h | 2 +- src/runtime/contrib/nnpack/convolution.cc | 2 +- src/runtime/contrib/nnpack/fully_connected.cc | 2 +- src/runtime/contrib/nnpack/nnpack_utils.h | 2 +- src/runtime/contrib/random/mt_random_engine.cc | 2 +- src/runtime/contrib/random/random.cc | 2 +- src/runtime/contrib/rocblas/rocblas.cc | 2 +- src/runtime/contrib/tensorrt/tensorrt_logger.h | 2 +- src/runtime/contrib/vitis_ai/vitis_ai_runtime.cc | 1 + src/runtime/cpu_device_api.cc | 2 +- src/runtime/crt/Makefile | 4 +- src/runtime/crt/graph_runtime/load_json.c | 2 +- src/runtime/file_utils.cc | 2 +- .../graph/cuda_graph/graph_runtime_cuda_graph.cc | 135 +++++++ src/runtime/graph/graph_runtime.cc | 7 +- src/runtime/graph/graph_runtime.h | 5 +- src/runtime/graph/graph_runtime_factory.cc | 33 ++ src/runtime/graph/graph_runtime_factory.h | 8 + src/runtime/hexagon/hexagon_device_api.cc | 2 +- src/runtime/hexagon/hexagon_module.cc | 2 +- src/runtime/hexagon/hexagon_module.h | 2 +- src/runtime/hexagon/sim/hexagon_device_sim.cc | 2 +- src/runtime/hexagon/target/hexagon_dsprpcapi.cc | 2 +- src/runtime/hexagon/target/hexagon_dsprpcapi.h | 2 +- src/runtime/hexagon/target/hexagon_stubapi.cc | 2 +- src/runtime/hexagon/target/hexagon_stubapi.h | 2 +- src/runtime/logging.cc | 151 +++++++ src/runtime/metal/metal_common.h | 2 +- src/runtime/micro/micro_session.cc | 2 +- src/runtime/minrpc/minrpc_server.h | 2 +- src/runtime/ndarray.cc | 2 +- src/runtime/object.cc | 2 +- src/runtime/opencl/opencl_common.h | 2 +- src/runtime/registry.cc | 2 +- src/runtime/rocm/rocm_device_api.cc | 2 +- src/runtime/rpc/rpc_device_api.cc | 4 +- src/runtime/rpc/rpc_endpoint.cc | 10 +- src/runtime/rpc/rpc_module.cc | 4 +- src/runtime/rpc/rpc_session.cc | 8 +- src/runtime/runtime_base.h | 6 +- src/runtime/thread_pool.cc | 2 +- src/runtime/threading_backend.cc | 2 +- src/runtime/vm/bytecode.cc | 2 +- src/runtime/vm/vm.cc | 2 +- src/runtime/vulkan/vulkan_common.h | 2 +- src/runtime/vulkan/vulkan_shader.h | 2 +- src/support/base64.h | 2 +- src/support/parallel_for.cc | 2 +- src/support/pipe.h | 2 +- src/support/socket.h | 2 +- src/target/llvm/llvm_common.cc | 2 +- src/target/source/source_module.cc | 2 +- src/target/spirv/ir_builder.cc | 2 + src/target/target.cc | 81 ++-- tests/cpp/ir_functor_test.cc | 2 +- tests/cpp/parallel_for_test.cc | 2 +- tests/lint/check_file_type.py | 2 + tests/python/driver/tvmc/test_frontends.py | 22 +- tests/python/frontend/tensorflow/test_forward.py | 52 ++- tests/python/relay/test_ir_parser.py | 8 +- tests/python/relay/test_ir_text_printer.py | 5 - .../relay/test_op_qnn_simulated_dequantize.py | 10 +- .../python/relay/test_op_qnn_simulated_quantize.py | 17 +- tests/python/topi/python/test_topi_qnn.py | 8 +- .../unittest/test_runtime_graph_cuda_graph.py | 100 +++++ .../test_runtime_module_based_interface.py | 30 ++ tests/scripts/task_build.sh | 2 +- tutorials/auto_scheduler/tune_network_cuda.py | 2 +- tutorials/auto_scheduler/tune_network_mali.py | 2 +- tutorials/auto_scheduler/tune_network_x86.py | 2 +- web/emcc/tvmjs_support.cc | 8 +- web/emcc/wasm_runtime.cc | 10 +- web/emcc/webgpu_runtime.cc | 25 +- 167 files changed, 2110 insertions(+), 781 deletions(-)
